R Programming Basics for Data Science and Machine Learning

Learn the rules for naming variables in R, including valid and invalid identifiers, allowed characters like underscores and dots, and how to view hidden objects in the environment.

Learn relational operators such as greater than, less than, greater than or equal to, less than or equal to, equal to, and not equal to, and how they evaluate conditions true or false.

Explore assignment operators, including left and right assignments, learn that the left side must be a variable, and practice using write assignment to assign values.

Explore miscellaneous operators in R, including the colon for sequence creation, the %in% operator for vector membership, and matrix multiplication with practical examples.

Explore how to define and call functions in R, including function names, parameters, bodies, and returns, with built-in functions, vectors, and mean and square roots.

Explore the data types in R, including numeric (double) and integer, logical, complex, character, and raw, and examine lists, data frames, matrices, and arrays.

Learn how to assign strings using double quotes or single quotes, print the string, and escape characters with backslashes in variables.

Explore the format() function for numeric data formatting, limiting decimals to three digits, converting between double and character types, and displaying values in scientific notation.

illustrates using the colon operator to generate vectors from one to ten, compares it with the sequence function, and explains single element vectors and type consistency in R.

Discover how to access vector elements with the square bracket operator and the c() function, performing single or multiple indexing and boolean subsetting.

Explore vector manipulation by performing element-wise arithmetic on vectors, including addition, subtraction, multiplication, and division, and understand vector recycling when sizes differ, and sorting in ascending or descending order.

Master list manipulation in R by accessing and updating elements, handling vectors, matrices, and booleans, and merging lists via concatenation to explore how data types and order shape results.

Explore how arrays extend matrices into multiple dimensions, build a three-dimensional arrangement from several two-dimensional matrices, and understand area sizes, dimensions, and element access.

Learn to create and manage one- to three-dimensional arrays and two-dimensional matrices, name rows and columns, and access specific elements across matrices in R.

Develop understanding of if, else, and else-if statements to handle single or multiple conditions, test conditions programmatically, and control flow for integer and double inputs.

Explore repeat and while loops, compare their syntax, and learn how count, increment, and conditions control execution, including how to avoid infinite loops.

Explore the for loop in contrast to while loops by iterating over a sequence or vector, printing elements, and using paste to combine index and value with customizable separators.

Explore the next and break statements in a for loop, showing how next skips the rest of an iteration and how break exits the loop when a condition is met.

Learn to create a data frame in R by assembling rainy-season vectors into a tabular set with days, temperature, humidity, and sky, and perform basic subsetting.

Learn to inspect a data frame using head, tail, str, and summary to view rows, structure, data types, and column names.

Learn to access data frame columns in R using square brackets, double brackets, and the dollar sign; compare bracket types and identify results as data frame, vector, or list.

Modify a data frame by transforming columns, such as adding 10 to temperature and humidity, while preserving the original data. Compare transforming to replace in place, including length-mismatch handling.

Learn to load a csv file into an R data frame using read.csv, explore the covid-19 dataset, inspect its columns and structure, and perform basic summary checks.

Load json data into a data frame in R by installing the json package, reading the file, converting to a data frame, and transposing to inspect its structure.

Learn to bind rows in R by combining data frames with rbind and bind_rows, using the dplyr package; handle unequal columns with bind_rows and understand when to use each method.

Apply conditional selection with subset() to filter data by country, identify the maximum confirmed cases and their dates, and understand cumulative sums versus new daily cases.

Sort data frames in R using the order method to arrange by confirmed cases, toggle ascending and descending, and inspect top results with head.

Group a data frame by date and country to sum covid cases, remove province and state duplicates, and drop latitude and longitude for accurate country-level totals.

Learn how to merge data frames using inner join on a date column, contrast with left and outer joins, and resolve suffixes to align worldwide and country covid data.

Master outer, left, and right joins in R to merge data frames, fill nulls for missing matches, and understand how union behavior shapes the combined data across keys.

Download and install Anaconda on Windows 10, configure the 64-bit graphical installer, run it in administrator mode, and launch Jupyter notebook for data science projects.

Install and initialize Anaconda on Linux by downloading the installer, running the .sh script, accepting the license, initializing the base environment, and verifying activation in the terminal.

Install and configure Anaconda, use administrator mode on Windows, then create and activate an R 4.x environment, install Jupyter notebook, and install the R kernel for notebooks.

Demonstrate how to start and manage a Jupyter notebook, including creating, renaming, and organizing cells, executing code, and using keyboard shortcuts for efficient data science workflows.

Master Jupyter notebook shortcuts for markdown, including embedding links and images, creating headings, tables, footnotes, task lists, and horizontal rules, with hints from a markdown cheat sheet on GitHub.

Compare and practice data science coding in jupyter notebook and r-studio, learn running cells, restarting kernels, preserving variables, using markdown, and exploring data frames with autocomplete.

Load the COVID-19 dataset in a Jupyter notebook, convert the date column, group by date and country, and identify the top 10 countries by cases for plotting.

Create a bar plot of the top ten worst hit covid-19 countries, with country names on the x-axis and confirmed cases on the y-axis, using color and ordering options.

Learn how to add a title, subtitle, and caption to a ggplot, customize fonts with element_text, adjust alignment with hjust, and explore labs vs ggtitle methods.

Learn to change text position and enlarge figure size by setting default styling in options and representation, then tune the alignment of title, subtitle, and caption for polished data visualizations.

Learn to create line plots for US covid-19 data, comparing confirmed, recovered, and deaths over time with single and multiple lines and color coding.

Explore the Boston housing data with a scatterplot to examine how median house prices relate to lower status population and population density, using color and size to highlight comparisons.

Explore pair plots and scatter matrix plots of the Boston housing dataset, analyzing 14 variables with diagonal density, Pearson correlation ellipses, and color plots to reveal variable relationships.

Clean the Titanic dataset in R by discarding rows with null values and converting numeric columns to categorical. Create a colored bar plot showing survival counts for 714 passengers.

Create scatter plots (point plots) for the Titanic dataset, using age on the x-axis and survived on the y-axis, with color and size to reveal density and trends.

Plot a histogram to visualize the distribution of a single continuous variable in data science, using bins, frequency counts, and adjustable bandwidth with axis labels.

Learn to create stacked histograms to compare survival across sex, age, fare, and passenger class in the Titanic dataset, with hands-on plotting and interpretation.

Plot the violin to visualize how a continuous variable distributes across categories, revealing age density and survival patterns by gender and passenger class.

Open the Jupiter notebook in an activated Anaconda base in administrator mode, navigate to your folder, and begin data processing and analysis with the tide and plot package.

Explore data preprocessing for data processing and analysis with tidyverse and dplyr, learning functions like select, filter, mutate, distinct, and count, using the pipe and managing package conflicts.

Learn how the select() method picks specific columns from a data frame, drops others with minus, and filters by starts with or ends with names in the covid-19 dataset.

Learn to use arrange to sort a data frame by a chosen column, with ascending or descending order, illustrated with date, country, confirmed cases, and deaths.

Group data by a chosen column to compute summary statistics across dates or countries, using sum, mean, and other operations on a dataframe for covid data.

Explore the pipeline operator, symbolized by %>% to chain multiple data transformations in a single line. Pass results between functions to enable group by and summarization in streamlined data workflow.

Explore the distinct() function in R to extract unique rows and countries from a dataset, compare it with unique(), and learn options like keep_all to preserve columns.

Summarize creates a new data frame by applying functions like mean, standard deviation, minimum, maximum, and count to columns. Group by country to generate per-country summaries.

Learn to use summarize_at, summarize_if, and summarize_all to automatically summarize selected numeric columns, apply conditional summaries, and group by country to find maximum values.

Slice a data frame by location with slice and slice_head to select first, last, or range rows; use slice_tail and max for insights from covid dataset from Johns Hopkins University.

Apply the between function from the deployer package to filter a dataset by numeric ranges, such as deaths between 100,000 and 1,000,000, and obtain the same results as alternative methods.

Explore cumall, cumany, and cummean to compute cumulative sums and cumulative means across vectors, with examples using a sample vector and conditionals like x > 5.

Learn to set up a Jupyter notebook, activate a conda environment, and use Plotly to analyze a covid-19 dataset from Johns Hopkins University, including data loading, preprocessing, and visualizing.

Load the covid-19 dataset from a GitHub repository, install and load required R packages, then read the data and sort by date to reveal country-level confirmed and death figures.

Learn to build an interactive line plot of daywise corona cases from a covid dataset using plotline, including data preprocessing, date sorting, and multi-trace lines for confirmed and death cases.

Learn to style line plots by customizing colors for confirmed, death, recovered, and active cases, adjusting line widths, and updating axis titles and plot layout.

Learn to customize markers in R plots by adjusting color, size, opacity, and outline for scatter and line plots using a marker parameter list.

Learn to extract the top 10 worst hit covid countries by the latest date and visualize them with a bar plot of confirmed cases in R.

Learn how to add direct labels to a bar chart by extracting values, converting them to text, and placing them automatically, while customizing colors and outlines.

Perform a complete case analysis for USA using subplots to compare confirmed, recovered, and death cases, with country filtering, date sorting, and color sequencing.

Create and compare pie charts of top 10 countries' covid-19 confirmed and death cases, highlighting percent contributions such as the United States and India.

Learn to plot a donut chart from a previous plot, add a hole of 0.6, remove an extra type, and display component and confirmed cases.

Explore the fundamentals of machine learning, supervised, unsupervised, reinforcement, and semi-supervised, along with regression, classification, and clustering, plus end-to-end workflows from data to deployment.

Explore linear regression through house price prediction on a Boston housing dataset, learn supervised learning concepts, independent versus dependent variables, and the fitted regression line.

Explore how regression models predict stock prices, tweet popularity, and house prices by using diverse input features such as recent history, data from related companies, sentiment, followers, and location attributes.

Identify simple and multiple linear regression, using one or more input variables to predict house prices, and interpret the loss function to reach minimum error on a plane or line.

Install and load the packages, compute a correlation matrix, and visualize it with a correlation plot to reveal how variables relate to median house price, including positive and negative correlations.

Analyze Boston crime data using the crime column, examine correlations with radius, taxes, and early start, and visualize with scatter plots to reveal positive links.

Analyze the top 10 percent of crime rates in the Boston data using 90th and 98th percentiles, and examine their relationship with lower status population and housing prices.

Examine the 90th percentile of areas with lower status in the Boston dataset, analyzing house prices, rooms, age, crime rate, and nitric oxide, and set up for linear regression.

Learn to build and train a simple linear regression model with a single input feature highly correlated with house prices, using the Boston dataset, with preprocessing and RMSE evaluation.

Analyze how to diagnose a linear regression model by interpreting null and alternate hypotheses, p-values and t-values, and assessing coefficient significance for feature selection.

Learn how r-squared measures explained variance and why adjusted r-squared corrects for model complexity, using rss, tss, residuals, and mean squared error.

Learn to build a multiple variable regression model by adding features, compare residual standard error and R-squared, and use p-values for variable importance to improve accuracy in non-linear data.